Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add newline53/newline-mcp-server --skill return-resolutiongit clone --depth 1 https://github.com/newline53/newline-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/newline53/newline-mcp-server/return-resolution)<a href="https://agentmods.dev/skills/newline53/newline-mcp-server/return-resolution"><img src="https://agentmods.dev/badge/skills/newline53/newline-mcp-server/return-resolution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/newline53/newline-mcp-server/return-resolution"><img src="https://agentmods.dev/badge/skills/newline53/newline-mcp-server/return-resolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.00798 |
| Opus 5.5 | $0.00021 | $0.00319 |
| Sonnet 5.5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
return-resolution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Return Resolution
Workflow for understanding and resolving a returned transfer on the Newline platform.
Step 1 — Identify the Return
If you have the return UID:
get-return uid=<return_uid>
If you need to find it:
list-returns
Record from the return:
uidoriginal_transaction_uid— the transaction that was returnedreturn_reason— the return reason code or descriptionamountandcurrencystatus— e.g.pending,processedprocessed_at— when the return was settled (null if still pending)
Step 2 — Retrieve the Original Transaction
get-transaction uid=<original_transaction_uid>
Record:
synthetic_account_uid— the account affectedtransfer_uid— the originating transfer (if applicable)transaction_type,amount,statuscustodial_account_uidbalance_after— the balance after the original transaction posted
Step 3 — Retrieve the Originating Transfer
If the transaction has a transfer_uid:
get-newline-transfer uid=<transfer_uid>
Record:
source_synthetic_account_uidanddestination_synthetic_account_uidinitiating_customer_uid- Transfer type (
ach,wire, orinstant_payment) and its fields usd_transfer_amountandstatus
For ACH returns the ach.sec_code and return reason code together
identify the specific NACHA return category (e.g. R01 Insufficient Funds,
R02 Account Closed, R03 No Account).
Step 4 — Check Transaction Events
list-transaction-events
Look for events where transaction_uid matches the original transaction UID.
A return event will typically show event_type containing "return" and the
reason in description or metadata.
Step 5 — Check Account Balance Impact
get-synthetic-account uid=<synthetic_account_uid>
Compare the current net_usd_balance against the balance_after recorded in
Step 2. The difference should reflect the return credit/debit.
Also check the synthetic line items for a return credit entry:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 108 lines · 53 tokens per session scan A 7f42c277900d
return-resolution is a skill published in the GitHub repository newline53/newline-mcp-server (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 798 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
return-resolution compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| return-resolutionnewline53/newline-mcp-server | Skill | 2 | 6mo ago | Apache-2.0 | A | 53 | Claude Code, Codex |
| surfBlockRunAI/blockrun-mcp | Skill | 389 | today | MIT | A | 110 | Claude Code, Codex |
| ib-trades-historystaskh/trading_skills | Skill | 404 | 3d ago | MIT | A | 59 | Claude Code |
| scanner-pmccstaskh/trading_skills | Skill | 404 | 3d ago | MIT | A | 63 | Claude Code |
| ib-collarstaskh/trading_skills | Skill | 404 | 3d ago | MIT | A | 30 | Claude Code |
| ib-portfolio-action-reportstaskh/trading_skills | Skill | 404 | 3d ago | MIT | A | 49 | Claude Code |
| calendarstaskh/trading_skills | Skill | 404 | 3d ago | MIT | A | 79 | Claude Code |